Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare read-only, idempotent, open-world, non-destructive behavior, and the description adds substantial context beyond that: pagination caps of 100 per side, a cost of 1 credit, and the important semantic warnings that 'no vote recorded' is not abstention and that published name lists can differ from official totals by one or two (with members_in_both_lobbies flagging duplicates).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The payload description is front-loaded in sentence one, and the trailing sentences each carry distinct information (paging limits, the abstention distinction, the teller/list mismatch caveat, and credit cost). It is dense with parentheticals and one long run of clauses, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden itself, and it names the key result fields (totals, winning side, party split, rebels, list_vs_official_count, members_in_both_lobbies) so the agent knows what it will receive. It also advises on pagination and the required division_id, matching the complexity of a single-resource lookup.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and each parameter already documents its type, range and default, so the description does not need to restate them. It only adds framing that the MP lists come back in pages of up to 100 per side with party filtering and offset paging, which is a marginal restatement of the schema rather than new semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource ('Get the full result of one House of Commons vote') and enumerates the payload: totals, winning side, party split, intra-party rebels, and names/constituencies per side. This clearly distinguishes it from commons_division_search, which is named as the source of the division_id.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete entry condition ('Use a division_id from commons_division_search'), two motivating questions it answers ('who voted against?', 'how did my MP vote?'), and a paging caveat. It does not explicitly state when to prefer lords_division_result instead, so the alternative routing is only implied by the 'House of Commons / UK Parliament' framing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.